Merge pull request #90 from harold-b/v1.1.0

v1.1.0 - Output buffering has been disabled (thanks @mocksoul) - Phase 1 sorting has been optimized with performance boost on average of 20 seconds+ - Allow displaying memo with the `--show-memo` switch. - Specify a memo for debugging with the `--memo` switch. - Disable automatic CPU affinity with the `--no-cpu-affinity` switch. See `bladebit --help` for more info on what this might be used for.
Chia-Network · Sep 12, 2021 · b48f262 · b48f262
2 parents f3fbfff + 83fd46e
commit b48f262
Show file tree

Hide file tree

Showing 44 changed files with 1,928 additions and 67 deletions.
diff --git a/.vscode/launch.json b/.vscode/launch.json
@@ -120,12 +120,18 @@
                 // ,"-t", "32"
 
             ],
+
             "stopAtEntry": false,
             "cwd": "${workspaceFolder}",
             "environment": [],
             "externalConsole": false,
             "MIMode": "gdb",
             "setupCommands": [
+                // {
+                //     "description": "Set scheduler locking to step",
+                //     "ignoreFailures": false,
+                //     "text": "set scheduler-locking step"
+                // },
                 {
                     "description": "Enable pretty-printing for gdb",
                     "text": "-enable-pretty-printing",

diff --git a/.vscode/settings.json b/.vscode/settings.json
@@ -4,15 +4,15 @@
         "nominmax"
     ],
     "files.associations": {
-        "*.sd": "yaml",
-        "*.userprefs": "xml",
         "Fastfile": "ruby",
         "*.plist": "xml",
+        "*.sd": "yaml",
         "*.json": "jsonc",
         "*.ir": "llvm",
         "*.qs": "javascript",
         "*.ac": "shellscript",
         "player": "json",
+        "*.userprefs": "xml",
         "memory": "cpp",
         "cstddef": "cpp",
         "string": "cpp",
@@ -81,7 +81,25 @@
         "complex": "cpp",
         "forward_list": "cpp",
         "typeindex": "cpp",
-        "valarray": "cpp"
+        "valarray": "cpp",
+        "__bit_reference": "cpp",
+        "__config": "cpp",
+        "__debug": "cpp",
+        "__errc": "cpp",
+        "__functional_base": "cpp",
+        "__hash_table": "cpp",
+        "__locale": "cpp",
+        "__mutex_base": "cpp",
+        "__node_handle": "cpp",
+        "__nullptr": "cpp",
+        "__split_buffer": "cpp",
+        "__string": "cpp",
+        "__threading_support": "cpp",
+        "__tree": "cpp",
+        "__tuple": "cpp",
+        "ios": "cpp",
+        "locale": "cpp",
+        "stack": "cpp"
     },
     "cSpell.words": [
         "Ryzen"

diff --git a/bladebit.vcxproj b/bladebit.vcxproj
@@ -222,6 +222,7 @@
 <ItemGroup>
   <!-- ClInclude's -->
   <ClInclude Include="src\algorithm\RadixSort.h"/>
+  <ClInclude Include="src\algorithm\YSort.h"/>
   <ClInclude Include="src\b3\blake3_impl.h"/>
   <ClInclude Include="src\b3\blake3.h"/>
   <ClInclude Include="src\bech32\segwit_addr.h"/>
@@ -260,10 +261,12 @@
   <ClInclude Include="src\Types.h"/>
   <ClInclude Include="src\Util.h"/>
   <ClInclude Include="src\util\Log.h"/>
+  <ClInclude Include="src\Version.h"/>
   <ClInclude Include="src\View.h"/>
 </ItemGroup>
 <ItemGroup>
   <!-- ClCompile's -->
+  <ClCompile Include="src\algorithm\YSort.cpp"/>
   <ClCompile Include="src\b3\blake3_avx2.c">
     <ExcludedFromBuild Condition="'$(Configuration)'=='release'">true</ExcludedFromBuild>
     <ExcludedFromBuild Condition="'$(Configuration)'=='debug'">true</ExcludedFromBuild>
@@ -344,6 +347,12 @@
     <ExcludedFromBuild Condition="'$(Configuration)'=='debug.arm'">true</ExcludedFromBuild>
     <ExcludedFromBuild Condition="'$(Configuration)'=='release.arm'">true</ExcludedFromBuild>
   </ClCompile>
+  <ClCompile Include="src\test\test_numa_sort.cpp">
+    <ExcludedFromBuild Condition="'$(Configuration)'=='release'">true</ExcludedFromBuild>
+    <ExcludedFromBuild Condition="'$(Configuration)'=='debug'">true</ExcludedFromBuild>
+    <ExcludedFromBuild Condition="'$(Configuration)'=='debug.arm'">true</ExcludedFromBuild>
+    <ExcludedFromBuild Condition="'$(Configuration)'=='release.arm'">true</ExcludedFromBuild>
+  </ClCompile>
   <ClCompile Include="src\threading\Semaphore.cpp"/>
   <ClCompile Include="src\threading\Thread.cpp"/>
   <ClCompile Include="src\threading\ThreadPool.cpp"/>
@@ -417,6 +426,7 @@
   <ClInclude Include="lib/include/relic/relic_util.h"/>
   <ClInclude Include="lib/include/relic/relic.h"/>
   <ClInclude Include="src/algorithm/RadixSort.h"/>
+  <ClInclude Include="src/algorithm/YSort.h"/>
   <ClInclude Include="src/b3/blake3_impl.h"/>
   <ClInclude Include="src/b3/blake3.h"/>
   <ClInclude Include="src/bech32/segwit_addr.h"/>
@@ -455,6 +465,7 @@
   <ClInclude Include="src/Types.h"/>
   <ClInclude Include="src/Util.h"/>
   <ClInclude Include="src/util/Log.h"/>
+  <ClInclude Include="src/Version.h"/>
   <ClInclude Include="src/View.h"/>
 </ItemGroup>
 

diff --git a/bladebit.vcxproj.filters b/bladebit.vcxproj.filters
@@ -99,6 +99,9 @@
     <ClInclude Include="src\algorithm\RadixSort.h">
       <Filter>src\algorithm</Filter>
     </ClInclude>
+    <ClInclude Include="src\algorithm\YSort.h">
+      <Filter>src\algorithm</Filter>
+    </ClInclude>
     <ClInclude Include="src\b3\blake3_impl.h">
       <Filter>src\b3</Filter>
     </ClInclude>
@@ -213,6 +216,9 @@
     <ClInclude Include="src\util\Log.h">
       <Filter>src\util</Filter>
     </ClInclude>
+    <ClInclude Include="src\Version.h">
+      <Filter>src</Filter>
+    </ClInclude>
     <ClInclude Include="src\View.h">
       <Filter>src</Filter>
     </ClInclude>
@@ -348,6 +354,9 @@
     <ClInclude Include="src/algorithm/RadixSort.h">
       <Filter>src/algorithm</Filter>
     </ClInclude>
+    <ClInclude Include="src/algorithm/YSort.h">
+      <Filter>src/algorithm</Filter>
+    </ClInclude>
     <ClInclude Include="src/b3/blake3_impl.h">
       <Filter>src/b3</Filter>
     </ClInclude>
@@ -462,11 +471,17 @@
     <ClInclude Include="src/util/Log.h">
       <Filter>src/util</Filter>
     </ClInclude>
+    <ClInclude Include="src/Version.h">
+      <Filter>src</Filter>
+    </ClInclude>
     <ClInclude Include="src/View.h">
       <Filter>src</Filter>
     </ClInclude>
   </ItemGroup>
   <ItemGroup>
+    <ClCompile Include="src\algorithm\YSort.cpp">
+      <Filter>src\algorithm</Filter>
+    </ClCompile>
     <ClCompile Include="src\b3\blake3_avx2.c">
       <Filter>src\b3</Filter>
     </ClCompile>
@@ -557,6 +572,9 @@
     <ClCompile Include="src\test\test_main.cpp">
       <Filter>src\test</Filter>
     </ClCompile>
+    <ClCompile Include="src\test\test_numa_sort.cpp">
+      <Filter>src\test</Filter>
+    </ClCompile>
     <ClCompile Include="src\threading\Semaphore.cpp">
       <Filter>src\threading</Filter>
     </ClCompile>

diff --git a/builds/linux/debug.arm.mk b/builds/linux/debug.arm.mk
@@ -2,6 +2,7 @@
 # Autogenerated by psync 1.2.0
 
 SOURCES += \
+	src/algorithm/YSort.cpp \
 	src/b3/blake3_dispatch.c \
 	src/b3/blake3_portable.c \
 	src/b3/blake3.c \

diff --git a/builds/linux/debug.mk b/builds/linux/debug.mk
@@ -2,6 +2,7 @@
 # Autogenerated by psync 1.2.0
 
 SOURCES += \
+	src/algorithm/YSort.cpp \
 	src/b3/blake3_avx2_x86-64_unix.S \
 	src/b3/blake3_avx512_x86-64_unix.S \
 	src/b3/blake3_dispatch.c \

diff --git a/builds/linux/debug.test.mk b/builds/linux/debug.test.mk
@@ -2,6 +2,7 @@
 # Autogenerated by psync 1.2.0
 
 SOURCES += \
+	src/algorithm/YSort.cpp \
 	src/b3/blake3_avx2_x86-64_unix.S \
 	src/b3/blake3_avx512_x86-64_unix.S \
 	src/b3/blake3_dispatch.c \
@@ -29,6 +30,7 @@ SOURCES += \
 	src/pos/chacha8.cpp \
 	src/SysHost.cpp \
 	src/test/test_main.cpp \
+	src/test/test_numa_sort.cpp \
 	src/threading/Semaphore.cpp \
 	src/threading/Thread.cpp \
 	src/threading/ThreadPool.cpp \

diff --git a/builds/linux/release.arm.mk b/builds/linux/release.arm.mk
@@ -2,6 +2,7 @@
 # Autogenerated by psync 1.2.0
 
 SOURCES += \
+	src/algorithm/YSort.cpp \
 	src/b3/blake3_dispatch.c \
 	src/b3/blake3_portable.c \
 	src/b3/blake3.c \

diff --git a/builds/linux/release.mk b/builds/linux/release.mk
@@ -2,6 +2,7 @@
 # Autogenerated by psync 1.2.0
 
 SOURCES += \
+	src/algorithm/YSort.cpp \
 	src/b3/blake3_avx2_x86-64_unix.S \
 	src/b3/blake3_avx512_x86-64_unix.S \
 	src/b3/blake3_dispatch.c \

diff --git a/builds/linux/release.test.mk b/builds/linux/release.test.mk
@@ -2,6 +2,7 @@
 # Autogenerated by psync 1.2.0
 
 SOURCES += \
+	src/algorithm/YSort.cpp \
 	src/b3/blake3_avx2_x86-64_unix.S \
 	src/b3/blake3_avx512_x86-64_unix.S \
 	src/b3/blake3_dispatch.c \
@@ -29,6 +30,7 @@ SOURCES += \
 	src/pos/chacha8.cpp \
 	src/SysHost.cpp \
 	src/test/test_main.cpp \
+	src/test/test_numa_sort.cpp \
 	src/threading/Semaphore.cpp \
 	src/threading/Thread.cpp \
 	src/threading/ThreadPool.cpp \

diff --git a/builds/macos/debug.arm.mk b/builds/macos/debug.arm.mk
@@ -2,6 +2,7 @@
 # Autogenerated by psync 1.2.0
 
 SOURCES += \
+	src/algorithm/YSort.cpp \
 	src/b3/blake3_dispatch.c \
 	src/b3/blake3_portable.c \
 	src/b3/blake3.c \

diff --git a/builds/macos/debug.mk b/builds/macos/debug.mk
@@ -2,6 +2,7 @@
 # Autogenerated by psync 1.2.0
 
 SOURCES += \
+	src/algorithm/YSort.cpp \
 	src/b3/blake3_avx2_x86-64_unix.S \
 	src/b3/blake3_avx512_x86-64_unix.S \
 	src/b3/blake3_dispatch.c \

diff --git a/builds/macos/debug.test.mk b/builds/macos/debug.test.mk
@@ -2,6 +2,7 @@
 # Autogenerated by psync 1.2.0
 
 SOURCES += \
+	src/algorithm/YSort.cpp \
 	src/b3/blake3_avx2_x86-64_unix.S \
 	src/b3/blake3_avx512_x86-64_unix.S \
 	src/b3/blake3_dispatch.c \
@@ -29,6 +30,7 @@ SOURCES += \
 	src/pos/chacha8.cpp \
 	src/SysHost.cpp \
 	src/test/test_main.cpp \
+	src/test/test_numa_sort.cpp \
 	src/threading/Semaphore.cpp \
 	src/threading/Thread.cpp \
 	src/threading/ThreadPool.cpp \

diff --git a/builds/macos/release.arm.mk b/builds/macos/release.arm.mk
@@ -2,6 +2,7 @@
 # Autogenerated by psync 1.2.0
 
 SOURCES += \
+	src/algorithm/YSort.cpp \
 	src/b3/blake3_dispatch.c \
 	src/b3/blake3_portable.c \
 	src/b3/blake3.c \

diff --git a/builds/macos/release.mk b/builds/macos/release.mk
@@ -2,6 +2,7 @@
 # Autogenerated by psync 1.2.0
 
 SOURCES += \
+	src/algorithm/YSort.cpp \
 	src/b3/blake3_avx2_x86-64_unix.S \
 	src/b3/blake3_avx512_x86-64_unix.S \
 	src/b3/blake3_dispatch.c \

diff --git a/builds/macos/release.test.mk b/builds/macos/release.test.mk
@@ -2,6 +2,7 @@
 # Autogenerated by psync 1.2.0
 
 SOURCES += \
+	src/algorithm/YSort.cpp \
 	src/b3/blake3_avx2_x86-64_unix.S \
 	src/b3/blake3_avx512_x86-64_unix.S \
 	src/b3/blake3_dispatch.c \
@@ -29,6 +30,7 @@ SOURCES += \
 	src/pos/chacha8.cpp \
 	src/SysHost.cpp \
 	src/test/test_main.cpp \
+	src/test/test_numa_sort.cpp \
 	src/threading/Semaphore.cpp \
 	src/threading/Thread.cpp \
 	src/threading/ThreadPool.cpp \

diff --git a/builds/win32/debug.arm.mk b/builds/win32/debug.arm.mk
@@ -2,6 +2,7 @@
 # Autogenerated by psync 1.2.0
 
 SOURCES += \
+	src/algorithm/YSort.cpp \
 	src/b3/blake3_dispatch.c \
 	src/b3/blake3_portable.c \
 	src/b3/blake3.c \

diff --git a/builds/win32/debug.mk b/builds/win32/debug.mk
@@ -2,6 +2,7 @@
 # Autogenerated by psync 1.2.0
 
 SOURCES += \
+	src/algorithm/YSort.cpp \
 	src/b3/blake3_avx2_x86-64_unix.S \
 	src/b3/blake3_avx512_x86-64_unix.S \
 	src/b3/blake3_dispatch.c \

diff --git a/builds/win32/debug.test.mk b/builds/win32/debug.test.mk
@@ -2,6 +2,7 @@
 # Autogenerated by psync 1.2.0
 
 SOURCES += \
+	src/algorithm/YSort.cpp \
 	src/b3/blake3_avx2_x86-64_unix.S \
 	src/b3/blake3_avx512_x86-64_unix.S \
 	src/b3/blake3_dispatch.c \
@@ -28,6 +29,7 @@ SOURCES += \
 	src/pos/chacha8.cpp \
 	src/SysHost.cpp \
 	src/test/test_main.cpp \
+	src/test/test_numa_sort.cpp \
 	src/threading/Semaphore.cpp \
 	src/threading/Thread.cpp \
 	src/threading/ThreadPool.cpp \

diff --git a/builds/win32/release.arm.mk b/builds/win32/release.arm.mk
@@ -2,6 +2,7 @@
 # Autogenerated by psync 1.2.0
 
 SOURCES += \
+	src/algorithm/YSort.cpp \
 	src/b3/blake3_dispatch.c \
 	src/b3/blake3_portable.c \
 	src/b3/blake3.c \

diff --git a/builds/win32/release.mk b/builds/win32/release.mk
@@ -2,6 +2,7 @@
 # Autogenerated by psync 1.2.0
 
 SOURCES += \
+	src/algorithm/YSort.cpp \
 	src/b3/blake3_avx2_x86-64_unix.S \
 	src/b3/blake3_avx512_x86-64_unix.S \
 	src/b3/blake3_dispatch.c \

diff --git a/builds/win32/release.test.mk b/builds/win32/release.test.mk
@@ -2,6 +2,7 @@
 # Autogenerated by psync 1.2.0
 
 SOURCES += \
+	src/algorithm/YSort.cpp \
 	src/b3/blake3_avx2_x86-64_unix.S \
 	src/b3/blake3_avx512_x86-64_unix.S \
 	src/b3/blake3_dispatch.c \
@@ -28,6 +29,7 @@ SOURCES += \
 	src/pos/chacha8.cpp \
 	src/SysHost.cpp \
 	src/test/test_main.cpp \
+	src/test/test_numa_sort.cpp \
 	src/threading/Semaphore.cpp \
 	src/threading/Thread.cpp \
 	src/threading/ThreadPool.cpp \

diff --git a/project.js b/project.js
@@ -158,6 +158,7 @@ bladebit.configs.test = () => config({
     ,src: [
 
         'src/test/test_main.cpp'
+        ,'src/test/test_numa_sort.cpp'
         // ,'src/test/TestNuma.cpp'
     ]
 

diff --git a/src/Config.h b/src/Config.h
@@ -4,6 +4,10 @@
 // #TODO: This should perhaps be named max jobs.
 #define MAX_THREADS 256
 
+// Perform Y sorts at the block level.
+// Unrolling loops by chacha block size.
+#define Y_SORT_BLOCK_MODE 1
+
 ///
 /// Debug Stuff
 ///
@@ -34,4 +38,6 @@
 // #define DBG_WRITE_LINE_POINTS 1
 // #define DBG_WRITE_SORTED_F7_TABLE 1
 
+// Enable to test plotting times without writing to disk
+// #define BB_BENCHMARK_MODE 1